Campaign Analytics
Document and analyze marketing A/B tests with hypothesis, design tables, targeting, and results lift reporting.
Overview
campaign-analytics is an agent skill for the Grow phase that structures A/B test hypotheses, design parameters, targeting, and results lift analysis for marketing campaigns.
Install
npx skills add https://github.com/alirezarezvani/claude-skills --skill campaign-analyticsWhat is this skill?
- If-then-because hypothesis block for campaign experiments
- Test design table: control vs variant, traffic split, MDE, confidence level, expected duration
- Targeting matrix for audience, channel, device, geography, and exclusions
- Results section with per-variant sample size, conversions, rate, and lift vs control
- Statuses for Planning, Running, Complete, and Inconclusive tests
Adoption & trust: 662 installs on skills.sh; 17.5k GitHub stars; 1/3 security scanners passed (skills.sh audits).
What problem does it solve?
You ran or planned a campaign test but lack a consistent write-up to judge significance and document learnings.
Who is it for?
Indie SaaS and ecommerce solo builders documenting email, landing page, or ad A/B tests in one standard format.
Skip if: Product analytics instrumentation setup, multivariate Bayesian tooling, or data pipelines without human-readable experiment conclusions.
When should I use this skill?
User needs A/B test analysis, campaign experiment documentation, hypothesis and results reporting for marketing variants.
What do I get? / Deliverables
You produce a complete A/B test report with design metadata and lift tables so you can ship or kill variants with documented rationale.
- Completed A/B test analysis document with design and results tables
- Documented test status and lift vs control
Recommended Skills
Journey fit
Campaign experiment readouts belong in Grow when you measure what channels and variants actually moved conversions. Analytics subphase is the home for structured test design, sample size, confidence level, and primary-metric lift tables.
How it compares
Markdown experiment report template—not a live stats engine or warehouse-connected analytics product.
Common Questions / FAQ
Who is campaign-analytics for?
Solo builders and small teams who run growth experiments and need agent help formatting hypotheses, metrics, and results without a dedicated experimentation SaaS.
When should I use campaign-analytics?
In Grow analytics when planning, running, or closing A/B tests on campaigns—after you have a primary metric and variant definitions.
Is campaign-analytics safe to install?
The skill is documentation templating; review the Security Audits panel on this Prism page for the parent skill package.
SKILL.md
READMESKILL.md - Campaign Analytics
# A/B Test Analysis **Test Name:** [Descriptive test name] **Test ID:** [Internal tracking ID] **Date:** [Start Date] - [End Date] **Status:** [Planning / Running / Complete / Inconclusive] --- ## Hypothesis **If** [we change X], **then** [Y will happen], **because** [rationale based on data or insight]. --- ## Test Design | Parameter | Detail | |-----------|--------| | **Variable Tested** | [What is being changed] | | **Control (A)** | [Description of control variant] | | **Variant (B)** | [Description of test variant] | | **Primary Metric** | [The main metric being measured] | | **Secondary Metrics** | [Additional metrics to monitor] | | **Traffic Split** | [50/50, 70/30, etc.] | | **Minimum Sample Size** | [Required sample per variant for statistical significance] | | **Minimum Detectable Effect** | [Smallest meaningful difference, e.g., 5% lift] | | **Confidence Level** | [95% or 99%] | | **Expected Duration** | [X days/weeks based on traffic and sample size] | --- ## Targeting | Criterion | Value | |-----------|-------| | **Audience** | [Who sees the test] | | **Channel** | [Where the test runs] | | **Device** | [All / Desktop / Mobile] | | **Geography** | [Regions included] | | **Exclusions** | [Who is excluded and why] | --- ## Results ### Primary Metric: [Metric Name] | Variant | Sample Size | Conversions | Rate | Lift vs Control | |---------|------------|-------------|------|----------------| | Control (A) | | | % | - | | Variant (B) | | | % | % | **Statistical Significance:** [Yes/No] at [X]% confidence **P-value:** [X.XXX] ### Secondary Metrics | Metric | Control (A) | Variant (B) | Lift | Significant? | |--------|------------|-------------|------|-------------| | [Metric 1] | | | % | [Yes/No] | | [Metric 2] | | | % | [Yes/No] | | [Metric 3] | | | % | [Yes/No] | --- ## Segment Analysis | Segment | Control Rate | Variant Rate | Lift | Notes | |---------|-------------|-------------|------|-------| | Desktop | % | % | % | | | Mobile | % | % | % | | | New Visitors | % | % | % | | | Returning Visitors | % | % | % | | | [Custom Segment] | % | % | % | | --- ## Revenue Impact Estimate | Metric | Value | |--------|-------| | **Projected Annual Lift** | [X]% | | **Projected Additional Revenue** | $[X] | | **Projected Additional Conversions** | [X] | | **Confidence in Estimate** | [High/Medium/Low] | --- ## Decision **Winner:** [Control / Variant / Inconclusive] **Rationale:** [Why this decision was made, citing specific metrics and statistical significance] **Implementation Plan:** - [ ] [Step 1: e.g., Roll out variant to 100% of traffic] - [ ] [Step 2: e.g., Update creative assets across campaigns] - [ ] [Step 3: e.g., Monitor for X days post-implementation] - [ ] [Step 4: e.g., Document learnings in knowledge base] --- ## Learnings **What we learned:** 1. [Key learning 1] 2. [Key learning 2] 3. [Key learning 3] **Follow-up tests to consider:** 1. [Next test idea based on results] 2. [Next test idea based on results] --- ## Quality Checks - [ ] Sample size reached minimum threshold - [ ] Test ran for at least 1 full business cycle (7 days minimum) - [ ] No external factors (holidays, outages, promotions) affected results - [ ] Segments were balanced between variants - [ ] No sample ratio mismatch (SRM) detected - [ ] Results reviewed by at least 2 team members --- *Template from campaign-analytics skill. Statistical significance calculations require external tools (e.g., online calculators or scipy).* # Campaign Performance Report **Report Period:** [Start Date] - [End Date] **Prepared By:** [Name] **Date:** [Report Date] --- ## Executive Summary [2-3 sentence summary of overall campaign performance, key wins, and areas of concern.] --- ## Portfolio Overview | Metric | This Period | Previous Period | Change | |--------|-----------|----------------|--------| | Total Spend | $ | $ | % | | Total Revenue | $ | $ | % | | Total Profit | $ | $ | % | | Portfolio ROI | % | % | pp | | Port